tanish78's picture
Update app.py
f1b7c2a verified
raw
history blame
6.72 kB
import gradio as gr
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
from sklearn.preprocessing import normalize
import re
from wordcloud import WordCloud
import matplotlib.pyplot as plt
def preprocess_data(df):
df.rename(columns={'Question Asked': 'texts'}, inplace=True)
df['texts'] = df['texts'].astype(str)
df['texts'] = df['texts'].str.lower()
df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
custom_synonyms = {
'application': ['form'],
'apply': ['fill', 'applied'],
'work': ['job'],
'salary': ['stipend', 'pay', 'payment', 'paid'],
'test': ['online test', 'amcat test', 'exam', 'assessment'],
'pass': ['clear', 'selected', 'pass or not'],
'result': ['outcome', 'mark', 'marks'],
'thanks': ["thanks a lot to you", "thankyou so much", "thank you so much", "tysm", "thank you",
"okaythank", "thx", "ty", "thankyou", "thank", "thank u"],
'interview': ["pi"]
}
for original_word, synonym_list in custom_synonyms.items():
for synonym in synonym_list:
pattern = r"\b" + synonym + r"\b(?!\s*\()"
df['texts'] = df['texts'].str.replace(pattern, original_word, regex=True)
pattern = r"\b" + synonym + r"\s+you" + r"\b(?!\s*\()"
df['texts'] = df['texts'].str.replace(pattern, original_word + ' ', regex=True)
spam_list = ["click here", "free", "recharge", "limited", "discount", "money back guarantee", "aaj", "kal", "mein",
"how can i help you", "how can we help you", "how we can help you", "follow", "king", "contacting", "gar",
"kirke", "subscribe", "youtube", "jio", "insta", "make money", "b2b","sent using truecaller"]
rows_to_remove = set()
for spam_phrase in spam_list:
pattern = r"\b" + re.escape(spam_phrase) + r"\b"
spam_rows = df['texts'].str.contains(pattern)
rows_to_remove.update(df.index[spam_rows].tolist())
df = df.drop(rows_to_remove)
greet_variations = ["hello", "hy", "hey", "hii", "hi", "heyyy", "bie", "bye"]
for greet_var in greet_variations:
pattern = r"(?<!\S)" + greet_var + r"(?!\S)|\b" + greet_var + r"\b"
df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
okay_variations = ["ok", "k", "kay", "okay", "okie", "kk", "ohhhk","t","r"]
for okay_var in okay_variations:
pattern = r"(?<!\S)" + okay_var + r"(?!\S)|\b" + okay_var + r"\b"
df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
yes_variations = ["yes", "yeah", "yep", "yup", "yuh", "ya", "yes got it", "yeah it is", "yesss", "yea","no"]
for yes_var in yes_variations:
pattern = r"(?<!\S)" + yes_var + r"(?!\S)|\b" + yes_var + r"\b"
df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
remove_phrases = ["i'm all set","ask a question","apply the survey","videos (2-8 min)","long reads (> 8 min)",
"short reads (3-8 min)","not a student alumni","mock","share feedback","bite size (< 2 min)",
"actually no","next steps","i'm a student alumni","i have questions"]
for phrase in remove_phrases:
df['texts'] = df['texts'].str.replace(phrase, '')
general_variations = ["good morning", "good evening", "good afternoon", "good night", "done", "sorry", "top", "query",
"stop", "sir", "sure", "oh", "wow", "aaa", "maam", "mam", "ma&#39;am","i'm all set","ask a question","apply the survey",
"videos (2-8 min)","long reads (> 8 min)","short reads (3-8 min)","not a student alumni","mock","share feedback","bite size (< 2 min)",
"actually no","next steps","i'm a student alumni","i have questions"]
for gen_var in general_variations:
pattern = r"(?<!\S)" + gen_var + r"(?!\S)|\b" + gen_var + r"\b(?=\W|$)"
df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
def remove_punctuations(text):
return re.sub(r'[^\w\s]', '', text)
df['texts'] = df['texts'].apply(remove_punctuations)
remove_morephrases = ["short reads 38 min","bite size 2 min","videos 28 min","long reads 8 min"]
for phrase in remove_morephrases:
df['texts'] = df['texts'].str.replace(phrase, '')
df = df[~df['texts'].str.contains(r'\b\d{10}\b')]
df['texts'] = df['texts'].str.strip()
df['texts'] = df['texts'].apply(lambda x: x.strip())
df = df[df['texts'] != '']
return df
def cluster_data(df, num_clusters):
vectorizer = TfidfVectorizer(stop_words='english')
X = vectorizer.fit_transform(df['texts'])
X = normalize(X)
kmeans = KMeans(n_clusters=num_clusters, random_state=0)
kmeans.fit(X)
df['Cluster'] = kmeans.labels_
return df, X, kmeans
def generate_wordcloud(texts):
wordcloud = WordCloud(width=800, height=400, background_color='white').generate(" ".join(texts))
plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
buf = BytesIO()
plt.savefig(buf, format='png')
buf.seek(0)
return buf
def main(file, num_clusters):
df = pd.read_csv(file)
# Filter by 'Fallback Message shown'
df = df[df['Answer'] == 'Fallback Message shown']
df = preprocess_data(df)
df, X, kmeans = cluster_data(df, num_clusters)
clusters = df['Cluster'].unique()
wordclouds = []
for cluster in clusters:
texts = df[df['Cluster'] == cluster]['texts'].tolist()
wordcloud_image = generate_wordcloud(texts)
wordclouds.append((f"Cluster {cluster}", wordcloud_image))
cluster_sizes = df['Cluster'].value_counts()
top_clusters = cluster_sizes.head(num_clusters).index
top_queries = df[df['Cluster'].isin(top_clusters)][['Cluster', 'texts']]
return wordclouds, top_queries
def display_results(wordclouds, top_queries):
for cluster, wordcloud in wordclouds:
print(cluster)
img = Image.open(wordcloud)
img.show()
print("Top Queries by Cluster:")
print(top_queries.to_string(index=False))
interface = gr.Interface(
fn=main,
inputs=[
gr.File(label="Upload CSV File (.csv)"),
gr.Slider(label="Number of Clusters", minimum=2, maximum=20, step=1, value=5)
],
outputs=[
gr.Gallery(label="Word Clouds of Clusters"),
gr.Dataframe(label="Top Queries by Cluster")
],
title="Unanswered User Queries Clustering",
description="Unanswered User Query Categorization"
)
interface.launch()